Analiza višemodalnih indikatora mentalne rezilijentnosti kao prediktora performanci pod stresom u simulacijskim vježbama

master's thesis

• Title (english): Analysis of multimodal indicators of mental resilience as predictors of performance under stress in simulation exercises
• Author: Tomislav Čuma
• Mentor: Siniša Popović (mentor)
• Committee member: Siniša Popović (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Mirko Sužnjević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-02-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U radu su procijenjene različite metode strojnog učenja i njihova sposobnost predviđanja ljudskih performanci na simulacijskim vježbama niske razine vjernosti iz domene kontrole zračnog prometa, primjenom multimodalnih značajki mentalne rezilijentnosti. Istražen je utjecaj različitih podskupova multimodalnih značajki na točnost predviđanja performanci. Otkriveno je da korištenje više značajki iz različitih podskupova općenito poboljšava rezultate predviđanja u usporedbi s korištenjem značajki iz samo jednog podskupa. Rad pruža uvid u važnost razmatranja različitih metoda strojnog učenja i skupova značajki mentalne rezilijentnosti za predviđanje performanci na simulacijskim vježbama u stresnim poslovima, što može imati potencijalni praktični značaj u kontekstu selekcije i obuke za visoko stresna zanimanja.

Abstract (english)

The thesis evaluated different machine learning methods and their ability to predict human performance in low-fidelity simulation exercises within the domain of air traffic control, using multimodal features of mental resilience. The impact of different subsets of multimodal features on the accuracy of performance prediction was investigated. Using multiple features from different subsets was generally found to improve prediction results compared to using features from only a single subset. The thesis provides insight into the importance of considering different machine learning methods and sets of mental resilience features for prediction of performance in simulation exercises in stressful jobs, which may have potential practical significance in the context of selection and training for highly stressful occupations.

• Keywords: stres; mentalna rezilijentnost; multimodalne značajke; strojno učenje; kontrola zračnog prometa
• Keywords (english): stress; mental resilience; multimodal features; machine learning; air traffic control
• Language: croatian
• URN:NBN: urn:nbn:hr:168:356100
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-07-13 10:00:36